Predicting Stock Volatility Research Articles

Heteroscedasticity effects as component to future stock market predictions using RNN-based models.

Heteroscedasticity effects are useful for forecasting future stock return volatility. Stock volatility forecasting provides business insight into the stock market, making it valuable information for investors and traders. Predicting stock volatility is a crucial task and challenging. This study proposes a hybrid model that predicts future stock volatility values by considering the heteroscedasticity element of the stock price. The proposed model is a combination of Generalized Autoregressive Conditional Heteroskedasticity (GARCH) and a well-known Recurrent Neural Network (RNN) algorithm Long Short-Term Memory (LSTM). This proposed model is referred to as GARCH-LSTM model. The proposed model is expected to improve prediction accuracy by considering heteroscedasticity elements. First, the GARCH model is employed to estimate the model parameters. After that, the ARCH effect test is used to test the residuals obtained from the model. Any untrained heteroscedasticity element must be found using this step. The hypothesis of the ARCH test yielded a p-value less than 0.05 indicating there is valuable information remaining in the residual, known as heteroscedasticity element. Next, the dataset with heteroscedasticity is then modelled using an LSTM-based RNN algorithm. Experimental results revealed that hybrid GARCH-LSTM had the lowest MAE (7.961), RMSE (10.466), MAPE (0.516) and HMAE (0.005) values compared with a single LSTM. The accuracy of forecasting was also significantly improved by 15% and 13% with hybrid GARCH-LSTM in comparison to single LSTMs. Furthermore, the results reveal that hybrid GARCH-LSTM fully exploits the heteroscedasticity element, which is not captured by the GARCH model estimation, outperforming GARCH models on their own. This finding from this study confirmed that hybrid GARCH-LSTM models are effective forecasting tools for predicting stock price movements. In addition, the proposed model can assist investors in making informed decisions regarding stock prices since it is capable of closely predicting and imitating the observed pattern and trend of KLSE stock prices.

The extra value of online investor sentiment measures on forecasting stock return volatility: A large-scale longitudinal evaluation based on Chinese stock market

Numerous studies have purported to show that using online investor sentiment measures can enhance the accuracy of forecasting stock return volatility. However, many of these studies did not validate their findings with out-of-sample data, had insufficient validation samples, or failed to incorporate appropriate controls in their predictive models. None of these studies compared the predictive power of online sentiment measures with commonly used technical sentiment measures, nor did they investigate whether online sentiment measures offer any additional predictive value for volatility forecasting when controlling for technical measures. Using a large stock sample in China A-shares, we contribute to examining the additional predictive power of online sentiment measures for predicting stock volatility for different forecast horizons and different time windows, while controlling for technical measures. Methodologically, through using rolling origins and moving windows evaluation framework, we consider the benefits of using global forecasting models compared to local stock-specific models, and the robustness of our appraisal of the use of sentiment measures. We found that technical sentiment measures generally perform better than online sentiments. When controlling for technical measures, online sentiment measures have extra predictive value only when the forecasting horizon is long (e.g., one week or month), but the magnitudes of the improvement are relatively limited.

Pricing of Chooser Option Based on Black-Scholes Model: Case of AAPL Company

Financial derivatives traded in the markets are becoming more complex and investors' complicated situations also should be responsible for this trend. This study examines the Black-Scholes Model theoretically and practically. By using the information of AAPL company, the simulation of stock price is calculated with related parameter, in the comparison of the straddle, the chooser option has a relatively high potential profit. The paper also gives sensitivity analysis and the conclusion of variables, the result is that the volatility has the largest impact on the stock price, followed by maturity period and date chosen period. Finally, this paper introduces wider application scenarios of our study, it can be used to estimate whether the future is bullish or bearish to obtain higher returns, to predict stock volatility, and to evaluate the value of growing companies, which fill the vacancy in past researches of financial market and gives suggestions for investors.

Investor sentiment based on scaled PCA method: A powerful predictor of realized volatility in the Chinese stock market

In this study, we construct an investor sentiment indicator (SsPCA) to predict stock volatility in the Chinese stock market by applying the scaled principal component analysis (sPCA). As a new dimension reduction technique for supervised learning, sPCA is employed to extract useful information from six individual sentiment proxies and obtain the common variations to characterize the investor sentiment (SsPCA). The empirical results indicate that SsPCA is a significant and powerful volatility predictor both in and out of sample. We also employ the partial least squares (PLS)-based investor sentiment index, three extra sentiment measures in past studies, and six individual sentiment proxies for comparison, and find SsPCA outperforms them on predicting stock volatility in the Chinese stock market. More importantly, the predictability of SsPCA remains significant before and after the famous financial crises (the sub-prime mortgage crisis and Chinese stock market turbulence) and the spread of the pandemic (COVID-19). Additionally, our findings imply that SsPCA still plays an essential role in predicting sock volatility after considering the leverage effect. The robustness of SsPCA in volatility forecasting is further verified in various industry indices of the Chinese stock market. Finally, we state that the strong predictability of SsPCA is highly related to its dimensionality reduction. Our results indicate that SsPCA is a robust volatility predictor from various aspects and performs better compared with existing sentiment indicators.

Macroeconomic attention, economic policy uncertainty, and stock volatility predictability

This study adopts the newly constructed macroeconomic attention indices (MAI) and category-specific economic policy uncertainty (EPU) indices to predict stock volatility. Principal component analysis (PCA), scaled PCA (sPCA), and partial least squares (PLS) are used to extract the principal components from indicators. The results show that the combination of MAI and EPU indices can obtain additional information for predicting stock market volatility. In addition, the comprehensive index containing all indicator information (FtAll) has the strongest short-term forecasting ability, whereas the MAI show the most substantial forecasting ability in long-term forecasting.

Research on Graph Neural Network in Stock Market

The stock market is a very important part of the financial field, and the prediction of the stock market has a great relationship with the returns and risk safety of the entire financial field. With the continuous mature application of machine learning and deep learning in other fields, such as image processing and text analysis, people begin to focus on the use of different models so as to predict stock volatility. However, in view of the unique multi-source and heterogeneous characteristics of stock information, the artificial neural network relying on deep learning cannot make a good prediction on it. At this time, the graph neural network that can well analyze the graph structure data is gradually favored by scholars at home and abroad, and the research thinking is also expanding. This dissertation examines the purpose of deeply analyzing the methods of different graph neural network models on stock prediction through an inductive study of amount of relevant literature. In this paper, we not only classify the literature by various graph neural network models, but also describe objectively the models and ideas presented in each paper. By referring to literature, this paper summarizes the previous research results, analyzes the applicability and results of different methods, and lays a foundation for better stock prediction in the future.

Realized skewness and the short-term predictability for aggregate stock market volatility

Forecasting stock volatility is of great interest to academics and practitioners because volatility has important implications for many areas such as risk management and portfolio allocation. Recent studies show that economic variables fail to predict stock volatility beyond lagged volatility. In this paper, we find that realized skewness shows significant predictive ability for future realized volatility. We use the daily price data of the S&P 500 index over a long sample period spanning 1928 to 2019 to construct skewness predictors, and reveal the negative relationship between realized skewness and volatility. The realized skewness significantly outperforms the benchmark of the autoregressive model in short horizons and contains different predictive information from macroeconomic indicators and volatility of volatility. The predictive ability of skewness is also found in most industry portfolios. The realized skewness predicts volatility mainly through risk transmission channel, and then through the business cycle channel.

A hybrid approach of adaptive wavelet transform, long short-term memory and ARIMA-GARCH family models for the stock index prediction

Modelling and forecasting the stock price constitute an important area of financial research for both academics and practitioners. This study seeks to determine whether improvements can be achieved by forecasting the stock index and volatility with the use of a hybrid model and incorporating the financial variables. We extend the literature of stock market forecasting by applying a hybrid model which combines adaptive wavelet transform (AWT), long short-term memory (LSTM) and ARIMAX-GARCH family models to predict stock index and combines AWT, LSTM and heterogeneous autoregressive model of realized volatility (HAR-RV) model to predict stock volatility for two major indexes in the U.S. stock market including the Dow Jones Industrial Average (DJIA) and Nasdaq Composite (IXIC). The results indicate an overall improvement in forecasting of stock index using the AWT-LSTM-ARMAX-FIEGARCH model with student’s t distribution as compared to the benchmark models. The robust test proves that this model has a higher prediction accuracy in prediction of different time horizons (1-, 10-, 15-, 20-, 30-, and 60-days ahead) for both stock indexes. Also, AWT-LSTM improves ability of HAR (3) X-RV model in prediction of the stocks realized volatility for mentioned time horizons.

What Types of Crowds Generate More Valuable Content? Evidence from Cross-Platform Posting

This study examines the value of content generated by various groups of users on a financial social media platform. The value of such content is measured by the incremental accuracy of predicting stock volatility based on the cues from those content. We argue that the characteristics of a crowd such as crowd size, crowd diversity, and crowd independence have significant impact on the predictive value of the crowd-generated content. Leveraging a natural experiment setup where the financial platform no longer receives cross-postings from another major social media platform, we show empirical evidence that the composition of crowds (i.e., characteristics of the users who make up crowds) does matter. Furthermore, the impacts of the characteristic features on the value of crowd-generated content are likely heterogeneous and non-monotone. Finally, we discuss the implications of this study about digital platform envelopment and competition.

A GARCH Model with Artificial Neural Networks

In this paper, we incorporate a GARCH model into an artificial neural network (ANN) for financial volatility modeling and estimate the parameters in Tensorflow. Our goal was to better predict stock volatility. We evaluate the performance of the models using the mean absolute errors of powers of the out-of-sample returns between 2 March 2018 and 28 February 2020. Our results show that our modeling procedure with an ANN can outperform the standard GARCH(1,1) model with standardized Student’s t distribution. Our variable importance analysis shows that Net Debt/EBITA is among the six most important predictor variables in all of the neural network models we have examined. The main contribution of this paper is that we propose a Long Short-Term Memory (LSTM) model with a GARCH framework because LSTM can systematically take into consideration potential nonlinearity in volatility structure at different time points. One of the advantages of our research is that the proposed models are easy to implement because our proposed models can be run in Tensorflow, a Python package that enables fast and automatic optimization. Another advantage is that the proposed models enable variable importance analysis.

Volatility modeling and prediction: the role of price impact

In this paper, we are interested in exploring the role of price impact, derived from the order book, in modeling and predicting stock volatility. This is motivated by the market microstructure literature that examines the mechanics of price formation and its relevance to market quality. Using a comprehensive dataset of intraday bids, asks, and three levels of market depths for 148 stocks in the Shanghai Stock Exchange from 2005 to 2016, we find substantial intraday impact from incoming bid and ask limit and market orders on stock prices. More importantly, the permanent price impact at the daily level is a significant determinant of stock volatility dynamics as suggested by the panel VAR estimation. Furthermore, when we augment traditional volatility models with the time series of daily price impact, the augmented models produce significantly more accurate volatility predictions at the one-day ahead forecasting horizon. These volatility predictions also offer economic gains to a mean-variance utility investor in a portfolio setting.

Improving volatility prediction and option valuation using VIX information: A volatility spillover GARCH model

AbstractWe develop a new generalized autoregressive conditional heteroskedasticity (GARCH) model that accounts for the information spillover between two markets. This model is used to detect the usefulness of the CBOE volatility index (VIX) for improving the performance of volatility forecasting and option pricing. We find the significant ability of VIX to predict stock volatility both in‐sample and out‐of‐sample. VIX information also helps to greatly reduce the option pricing error. The proposed volatility spillover GARCH model performs better than the related approaches proposed by Kanniainen et al. (2014, J Bank Finance, 43, pp. 200‐211) and P. Christoffersen et al. (2014, J Financ Quant Anal, 49, pp. 663–697).

Volatility Modeling and Prediction: The Role of Price Impact

In this paper, we are interested in exploring the role of price impact, derived from the order book, in modeling and predicting stock volatility. This is motivated by the microstructure literature that focuses on the mechanics of price formation and its relevance to market quality. Using a comprehensive dataset of intraday bids, asks, and three levels of market depths for 148 stocks in the Shanghai Stock Exchange from 2005 to 2016, we find substantial intraday impact from buy and sell limit and market orders on stock prices. More importantly, the permanent price impact at the daily level is a significant determinant in the volatility estimation for all sample stocks as shown by the panel VAR estimation, which allows us to examine simultaneously the dynamics of price impact on all sample stocks. Furthermore, when we augment traditional volatility models with the time series of daily price impact, the augmented models produce significantly more accurate forecasts at the one-day horizon. These forecasts from the augmented models offer economic gains to a mean-variance utility investor in a portfolio setting.

Forecasting stock volatility using after-hour information: Evidence from the Australian Stock Exchange

Since markets generally do not trade during overnight period, volatility cannot be estimated on a high-frequency basis. We adopt a new forecasting approach by using squared overnight return, pre-open volatility of the same asset and realized volatilities of related assets from other markets, where intraday data is still available while the Australian Stock Exchange (ASX) is closed, to predict stock volatility. We use a number of different specifications of the Heterogeneous Autoregressive (HAR) model to identify an optimal way to incorporate this additional information. We evaluate the forecasting performance of 45 ASX 200 stocks, categorized in three groups based on their annual total trading volumes, three Global Industry Classification Standard (GICS) indices and the S&P/ASX 200 index using a rolling estimation method. Our empirical analysis of the ASX constituents confirms the usefulness of using pre-open volatility of the same asset and realized volatilities of related assets from other markets when the ASX is closed for forecasting future volatility. Furthermore, we find that the predictive power of overnight information for all stocks and indices is higher during the market opening period and declines gradually over the trading day. However, the decrement is steeper for active stocks, suggesting that the predictive power is higher for inactively traded stocks. Finally, we evaluate the economic significance of the augmented HAR model that includes realized volatilities of related assets from other markets, and we find that it provides significant utility gains to a typical mean-variance investor.

Predicting stock volatility using after-hours information: Evidence from the NASDAQ actively traded stocks

We use realized volatilities based on after-hours high frequency stock returns to predict next day stock volatility. We extend the GARCH model to include additional information: the whole after hours period, the preopen realized variance, the postclose realized variance, and the overnight squared return. For the thirty most active NASDAQ stocks, we find that most of the stocks exhibit positive and significant preopen coefficients and that the inclusion of the preopen variance can mostly improve the out-of-sample forecastability of the next day conditional volatility. The inclusions of the postclose variance and overnight squared returns do provide some predictive power for the next day conditional volatility, but to a lesser degree; their predictive abilities are inferior to that of the preopen variance. Our findings support the results of prior studies: traders trade mostly for non-information reasons in the postclose period and trade mostly for information reasons in the preopen period.